Triple

T26775009
Position Surface form Disambiguated ID Type / Status
Subject Couchey E670093 entity
Predicate wineClassificationArea P97874 FINISHED
Object Marsannay AOC
Marsannay AOC is a Burgundy wine appellation in eastern France known for producing red, white, and rosé wines, particularly from Pinot Noir and Chardonnay grapes.
 E1745656 NE FINISHED

How this triple was built (3 steps)

Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.

NER Named-entity recognition gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Marsannay AOC | Statement: [Couchey, wineClassificationArea, Marsannay AOC]
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Marsannay AOC
Triple: [Couchey, wineClassificationArea, Marsannay AOC]
Generated description
Marsannay AOC is a Burgundy wine appellation in eastern France known for producing red, white, and rosé wines, particularly from Pinot Noir and Chardonnay grapes.
PD Predicate disambiguation gpt-5-mini-2025-08-07 
Target predicate: wineClassificationArea
Context triple: [Couchey, wineClassificationArea, Marsannay AOC]
  • A. wineClassificationRegion
    Indicates that a wine is classified according to the geographic region where it is produced or designated.
  • B. wineRegionCategory chosen
    Indicates a classification relationship where a wine region is assigned to a specific category or type of wine-producing area.
  • C. wineRegion
    Indicates the geographical region or area where a particular wine is produced or originates.
  • D. wineLawRegionType
    Indicates the type or category of legal designation that governs wine production in a particular region.
  • E. wineLawRegionName
    Indicates that a specific name refers to the legal wine-producing region defined by wine regulations.
  • F. None of above.

Provenance (6 batches)

The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.

Step Stage Batch ID Status When
creating Elicitation batch_69eeb31c925881909b597f6e40056d28 completed April 27, 2026, 12:51 a.m.
NER Named-entity recognition batch_69f6193170a88190adbbb22150475bb5 completed May 2, 2026, 3:33 p.m.
NED1 Entity disambiguation (via context triple) batch_6a12132e1f7c8190b55d411f437e7247 completed May 23, 2026, 8:50 p.m.
NEDg Description generation batch_6a121416401481908c0fa6e1c2e9e317 completed May 23, 2026, 8:54 p.m.
NED2 Entity disambiguation (via description) batch_6a1217e349a08190a986e6ce56f5b82d completed May 23, 2026, 9:10 p.m.
PD Predicate disambiguation batch_69f611ad2eb48190ac1ed0090f13f7a9 completed May 2, 2026, 3:01 p.m.
Created at: April 27, 2026, 4:04 a.m.